Ctrl+K

3 contributors

History: 22 commits

Luigi

Load ./libmmdeploy_tensorrt_ops.so for TensorRT EP if available

1c5dc58 over 2 years ago

video
Add a sample video over 2 years ago
.gitattributes

1.66 kB
Add a sample video over 2 years ago
README.md

1.47 kB
Update README.md over 2 years ago
constant_folding.sh

337 Bytes
Apply constant folding over 2 years ago
convert_to_fp16.py

1.11 kB
Fix FP16 models having poor accuracy over 2 years ago
convert_to_fp16_all.py

1.36 kB
Bugfix: correct batch dimension fixation then regenerate ONNX models over 2 years ago
demo.sh

56 Bytes
Remove models with fixed batch size as dynamic batch is generally supported over 2 years ago
demo_batch.sh

64 Bytes
Remove models with fixed batch size as dynamic batch is generally supported over 2 years ago
rtmo-l.fp16.onnx

88 MB
xet

Apply constant folding over 2 years ago
rtmo-l.onnx

176 MB
xet

Apply constant folding over 2 years ago
rtmo-m.fp16.onnx

44.7 MB
xet

Apply constant folding over 2 years ago
rtmo-m.onnx

89.3 MB
xet

Apply constant folding over 2 years ago
rtmo-s.fp16.onnx

19.9 MB
xet

Apply constant folding over 2 years ago
rtmo-s.onnx

39.6 MB
xet

Apply constant folding over 2 years ago
rtmo-t.fp16.onnx

13.7 MB
xet

Apply constant folding over 2 years ago
rtmo-t.onnx

27.4 MB
xet

Apply constant folding over 2 years ago
rtmo_demo.py

2.18 kB
Add option --yolo_nas_pose, used to read YOLO NAS Pose model instead of RTMO over 2 years ago
rtmo_demo_batch.py

3.15 kB
Bugfix for batch demo: add padding if remaning number of frames is not equal to batch size over 2 years ago
rtmo_gpu.py

17.9 kB
Load ./libmmdeploy_tensorrt_ops.so for TensorRT EP if available over 2 years ago
symbolic_shape_infer.py

138 kB
Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider over 2 years ago
symbolic_shape_infer_all.sh

135 Bytes
Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider over 2 years ago